© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110131
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conditional statements or assumptions in a programming or mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     такой
    -0.45
     таким
    -0.43
     такого
    -0.40
     такое
    -0.40
     такую
    -0.40
     такая
    -0.40
     таке
    -0.37
     такие
    -0.37
     takie
    -0.35
     taki
    -0.35
    POSITIVE LOGITS
    ########.
    0.68
    endphp
    0.66
     BoxFit
    0.64
     propOrder
    0.62
     betweenstory
    0.62
     الاطلاع
    0.60
     Réponses
    0.60
     Signalez
    0.57
    RegistryLite
    0.56
    msgTypes
    0.55
    Activations Density 0.000%

    No Known Activations